Model comparison
Kimi K2 (Jul 2025) vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 43.8 to 40.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 22.7.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 (Jul 2025) | Step 5 Preview | |
|---|---|---|
| Provider | Moonshot AI | StepFun |
| Noometry Index | 40.9 | 43.8 |
| Released | 2025-07-12 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.02M |
| Max output | 262K | 66K |
| Input $ / M tokens | $0.57 | $1 |
| Output $ / M tokens | $2.30 | $2.70 |
| Results tracked | 42 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Kimi K2 (Jul 2025): 43.1 (#83), Step 5 Preview: 50.6 (#40)
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1569 |
| SciCode | — | 58.9% |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| LMArena Coding | 1399 | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.2 (#59), Step 5 Preview: —
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Step 5 Preview leads
Kimi K2 (Jul 2025): 22.7 (#173), Step 5 Preview: 38.0 (#58)
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| CritPt | — | 20.9% |
| LMArena Hard Prompts | 1384 | — |
| Epoch Capabilities Index | 146.02 | — |
| ForecastBench | 60.2 | — |
Math Not comparable
Kimi K2 (Jul 2025): 40.1 (#81), Step 5 Preview: —
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| Omni-MATH | 65.4% | — |
| LMArena Math | 1396 | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Not comparable
Kimi K2 (Jul 2025): 36.9 (#153), Step 5 Preview: —
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
| LMArena Expert | 1363 | — |
Multilingual Not comparable
Kimi K2 (Jul 2025): 49.8 (#125), Step 5 Preview: —
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1372 | — |
| LMArena Chinese | 1416 | — |
| LMArena French | 1379 | — |
| LMArena German | 1386 | — |
| LMArena Japanese | 1349 | — |
| LMArena Korean | 1324 | — |
| LMArena Russian | 1384 | — |
| LMArena Spanish | 1383 | — |
Instruction Following Not comparable
Kimi K2 (Jul 2025): 71.3 (#151), Step 5 Preview: —
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| IFEval | 85% | — |
| LMArena Instruction Following | 1347 | — |
Long Context Not comparable
Kimi K2 (Jul 2025): 41.2 (#140), Step 5 Preview: —
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
| LMArena Longer Query | 1353 | — |
Writing & Preference Not comparable
Kimi K2 (Jul 2025): 62.5 (#76), Step 5 Preview: —
| Benchmark | Kimi K2 (Jul 2025) | Step 5 Preview |
|---|---|---|
| LMArena Text | 1380 | — |
| LMArena Creative Writing | 1349 | — |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
| LMArena Multi-Turn | 1371 | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 43.8 to 40.9 on the Noometry Index.
Which is cheaper, Kimi K2 (Jul 2025) or Step 5 Preview?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Kimi K2 (Jul 2025) or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 50.6 versus 43.1 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 262K.
How many benchmarks do Kimi K2 (Jul 2025) and Step 5 Preview share?
0 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Step 5 Preview has 3.